implement
01Command
RPI phase 3 — execute a plan step by step and run the quality gate.
Command
RPI phase 3 — execute a plan step by step and run the quality gate.
Command
Triage and patch one or more CVEs: fix via package overrides, Dockerfile upgrade, or add a trivyignore entry.
Command
RPI phase 2 — turn a research doc into a numbered implementation plan.
Command
RPI phase 1 — research the codebase for a task and write a research doc.
Command
Create or refresh a project-specific defensive security profile skill.
Command
Scaffold a new skill folder with SKILL.md, GOTCHAS.md, HISTORY.md, and starter directories.
Command
RPI helper - update an existing plan with newly answered questions.
Skill Claude CodeCodex
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
Skill Claude CodeCodex
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
Skill Claude CodeCodex
Token-efficient response mode: concise, exact, no fluff, no unnecessary wrapping. Always use and persist until user says "normal mode".
Skill Claude CodeCodex
Orchestrator-only workflow for heavy coding sessions, multi-phase implementation, and risky refactors. Use for complex work that needs planning, review gates, and persistent progress tracking.
Skill Claude CodeCodex
A relentless interview to sharpen a plan or design.
Skill Claude CodeCodex
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Skill Claude CodeCodex
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security…
Skill Claude CodeCodex
Always used to reduce overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Claude CodeCodex
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
Skill Claude CodeCodex
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
Skill Claude CodeCodex
Test an oh-my-opencode-slim release candidate or bugfix before publishing. Use when validating a packed plugin artifact, release branch, crash fix, OpenCode runtime compatibility, or model-specific smoke test such as OpenCode 1.17.11 message transform regressions.
Skill Claude CodeCodex
Use when establishing or reviewing a defensive security baseline across projects: threat model, auth/authz, validation, secrets, deps, logging, disclosure.
Skill Claude CodeCodex
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.
Skill Claude CodeCodex
Cut AI tells from any writing. Must always apply.
Skill Claude CodeCodex
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.
Skill Claude CodeCodex
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.